Available now

FLUX.2 [flex]: text to image

By Black Forest Labs

Black Forest Labs' FLUX.2 [flex] makes an image from a written prompt and lets you set the steps and guidance yourself.

Model ID
Maker
Black Forest Labs

Input

Fields marked * are required. Review the price before generating.

Example prompt. Edit it or write your own.

Additional settings

The safety tolerance level for the generated image. 1 being the most strict and 5 being the most permissive.

The number of inference steps to perform.

Price$0.08 / run

You sign up first. Your settings are kept.

About this model

Overview

FLUX.2 [flex] works from text alone, in six square, portrait or landscape sizes, as JPEG or PNG. Steps run from 2 to 50 and the guidance scale from 1.5 to 10, so you can trade a quick rough render for a slower, more detailed one.

What you can build

  • Posters and covers with titles in the image
  • Detailed illustrations where extra steps pay off
  • Fast low-step drafts before a final render
  • Header and banner images in landscape sizes

Prompting tips

  • Put any text you want in the image in quotes and name the font style, such as bold serif or hand lettering.
  • Draft with few steps, then raise the steps for the version you keep with the same seed.
  • Raise the guidance when parts of the prompt are missing; lower it for a softer, freer look.

What to check

Inspect the full-size output and compare details and subject appearance with your source.

Inputs

  • Prompt (required): The prompt to generate an image from.
  • Image Size (optional): The size of the generated image. Options: Square HD, Square, Portrait 4:3, Portrait 16:9, Landscape 4:3, Landscape 16:9.
  • Seed (optional): The seed to use for the generation.
  • Safety Tolerance (optional): The safety tolerance level for the generated image. 1 being the most strict and 5 being the most permissive. Options: 1, 2, 3, 4, 5.
  • Output Format (optional): The format of the generated image. Options: jpeg, png.
  • Guidance Scale (optional): The guidance scale to use for the generation. From 1.5 to 10.
  • Number of Inference Steps (optional): The number of inference steps to perform. From 2 to 50.

Output and limits

  • Image sizes: Square HD (1024×1024), Square (512×512), Portrait 4:3 (768×1024), Portrait 16:9 (576×1024), Landscape 4:3 (1024×768), Landscape 16:9 (1024×576).
  • File formats: JPEG, PNG.
  • Small or dense text in the image can come out misspelled.
  • Hands, crowds and complex poses can show artifacts; generate a few variations and pick the best.
  • Some prompts or outputs can be refused by safety checks.

Price guide

  • up to, default options: $0.08 / run